Semantic interpretation for convolutional neural networks: What makes a cat a cat?

by   Hao Xu, et al.

The interpretability of deep neural networks has attracted increasing attention in recent years, and several methods have been created to interpret the "black box" model. Fundamental limitations remain, however, that impede the pace of understanding the networks, especially the extraction of understandable semantic space. In this work, we introduce the framework of semantic explainable AI (S-XAI), which utilizes row-centered principal component analysis to obtain the common traits from the best combination of superpixels discovered by a genetic algorithm, and extracts understandable semantic spaces on the basis of discovered semantically sensitive neurons and visualization techniques. Statistical interpretation of the semantic space is also provided, and the concept of semantic probability is proposed for the first time. Our experimental results demonstrate that S-XAI is effective in providing a semantic interpretation for the CNN, and offers broad usage, including trustworthiness assessment and semantic sample searching.



There are no comments yet.


page 3

page 6

page 8

page 11

page 24

page 28

page 30

page 32


Visual Interpretability for Deep Learning: a Survey

This paper reviews recent studies in emerging directions of understandin...

Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

Explainable AI (XAI) is an active research area to interpret a neural ne...

Multiblock-Networks: A Neural Network Analog to Component Based Methods for Multi-Source Data

Training predictive models on datasets from multiple sources is a common...

Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models

(Artificial) neural networks have become increasingly popular in mechani...

Explainable Learning: Implicit Generative Modelling during Training for Adversarial Robustness

We introduce Explainable Learning ,ExL, an approach for training neural ...

Convolutional Neural Network Interpretability with General Pattern Theory

Ongoing efforts to understand deep neural networks (DNN) have provided m...

Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation

With the wide use of deep neural networks (DNN), model interpretability ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.